← Back to community benchmarks

gemma-4-26b-a4b-it

M4 (10c) · 32 GB · 4bit · 2026-05-06
Performance
16k
tokens
798.9
PP tok/s
10.4
TG tok/s
20509
TTFT (ms)
16.4
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.3.8
macOS macOS 26.3.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 369.4 32.7 14.6 GB view
4k 376.3 32.3 15.3 GB view
8k 366.2 30.6 15.4 GB view
16k 798.9 10.4 16.4 GB current
32k 712.2 11.0 17.3 GB view
64k 580.9 10.5 18.1 GB view
Batching Results
Batch Size TG tok/s Speedup
32.7 1.00×
49.6 1.52×
57.7 1.76×
65.8 2.01×